"""Overview / dashboard home page."""
from __future__ import annotations

import sys
from pathlib import Path

sys.path.insert(0, str(Path(__file__).resolve().parents[1]))

import pandas as pd
import streamlit as st

from utils import data_loader as dl
from utils.plotting import montana_with_hospitals
from utils.styling import callout, page_setup, section, INITIATIVE_COLOR


page_setup("Overview")

# --------------------------------------------------------------------------
# Brand strip + headline
# --------------------------------------------------------------------------
st.markdown(
    "<div class='rhtp-brandbar'>"
    "<div>"
    "<div class='kicker'>Montana DPHHS &middot; Rural Health Transformation Program</div>"
    "<h1>RHTP Evaluation Dashboard</h1>"
    "<div class='subtitle'>A fixed research plan, layered, causal evaluation of all five "
    "RHTP initiatives across Montana's 56 counties and 65 hospitals.</div>"
    "</div></div>",
    unsafe_allow_html=True,
)

# --------------------------------------------------------------------------
# Top-line stats
# --------------------------------------------------------------------------
counties = dl.counties()
hosp = dl.hospitals()
fq = dl.facility_quarter_ops()
coe = dl.coe_implementation()
wf = dl.workforce_panel()

c1, c2, c3, c4, c5 = st.columns(5)
with c1:
    st.metric("Hospitals tracked", f"{len(hosp):,}",
              help="Critical Access, PPS, Tertiary, Sole Community, and Tribal/IHS facilities.")
with c2:
    rural = (counties["rurality"] != "Urban").sum()
    st.metric("Rural / tribal counties", f"{rural} / {len(counties)}")
with c3:
    treated = (coe["coe_cohort"] != "never").sum()
    st.metric("CoE-enrolled facilities", f"{treated} / {len(hosp)}",
              delta=f"{treated/len(hosp):.0%}", delta_color="off")
with c4:
    latest = fq.sort_values(["year", "quarter"]).groupby("facility_id").tail(1)
    neg_margin = (latest["operating_margin_pct"] < 0).sum()
    st.metric("Negative-margin hospitals (latest Q)",
              f"{neg_margin} / {len(latest)}",
              delta=f"{neg_margin/len(latest):.0%}", delta_color="off")
with c5:
    pop = counties["population_2020"].sum()
    st.metric("Population covered", f"{pop:,.0f}")

# --------------------------------------------------------------------------
# Evaluation framing
# --------------------------------------------------------------------------
section("Evaluation framing",
        "How this dashboard is structured and what each page answers.")

c1, c2 = st.columns([3, 2])
with c1:
    st.markdown(
        "Every initiative page follows the same three-section pattern:\n\n"
        "1. **Initiative scope** — KPOs (with baseline + FY2031 target + level) "
        "and treatment / intervention inputs, so you know exactly what each "
        "page is trying to move and which levers it pulls.\n"
        "2. **Data Explorer** — interactive panel of the underlying outcomes "
        "and treatments.\n"
        "3. **Models** — the exact econometric specification(s) for that "
        "initiative, with adjustable knobs so a stakeholder can see *how* an "
        "estimate is constructed.\n"
        "4. **Was the initiative successful?** — direction, magnitude, "
        "precision, timing, consistency, and dose-response, applied to the "
        "model's outputs.\n\n"
        "This structure mirrors the **RHTP_models_full** modeling playbook."
    )
    callout(
        "<strong>About the data.</strong> Every file in <code>/data/</code> is "
        "<strong>synthetic</strong>, generated by <code>scripts/generate_data.py</code> "
        "to mirror the schema and units of the real source feeds — CMS Hospital "
        "Cost Reports, Montana Medicaid claims, HRSA workforce data, BRFSS, "
        "Big Sky Care Connect HIE rosters, and the MT DPHHS facility / county "
        "files. Treatment effects are baked in deterministically (with realistic "
        "noise), so the models <em>should</em> recover positive effects on the "
        "outcomes the RHTP plan is designed to move. To switch the dashboard to "
        "live data, drop a real file with the same name and column schema into "
        "<code>/data/</code> — no code changes needed.",
        kind="info",
    )

with c2:
    st.markdown("##### Five initiatives")
    initiatives = [
        ("01", "Workforce"),
        ("02", "Facility Sustainability"),
        ("03", "Innovative Care & Payment"),
        ("04", "Community Prevention"),
        ("05", "Technology & Data"),
    ]
    for num, name in initiatives:
        color = INITIATIVE_COLOR[int(num)]
        st.markdown(
            f"<div class='rhtp-card' style='border-left:5px solid {color};'>"
            f"<div style='display:flex; align-items:baseline; gap:10px;'>"
            f"<span style='color:{color}; font-weight:700; "
            f"letter-spacing:0.06em; font-size:0.78rem;'>INITIATIVE {num}</span>"
            f"<h4 style='margin:0;'>{name}</h4></div>"
            f"<div style='color:#9CA3AF; font-size:0.85rem; margin-top:4px;'>"
            f"open via the sidebar</div></div>",
            unsafe_allow_html=True,
        )

# --------------------------------------------------------------------------
# Map
# --------------------------------------------------------------------------
section("Montana hospitals by county",
        "Hover any county for population and rurality; hover any marker for the "
        "hospital name, facility type, staffed beds, ownership, and CCN.")

ctrl_col, _ = st.columns([3, 1])
with ctrl_col:
    facility_types = sorted(hosp["facility_type"].unique().tolist())
    selected_types = st.multiselect(
        "Facility types to display",
        options=facility_types,
        default=facility_types,
        help="Filter the map markers. The choropleth always shows all 56 counties.",
    )

if not selected_types:
    selected_types = facility_types

fig = montana_with_hospitals(counties, hosp, facility_type_filter=selected_types,
                             height=620)
st.plotly_chart(fig, use_container_width=True, config={"displaylogo": False})

fcount = hosp[hosp["facility_type"].isin(selected_types)]
beds_total = int(fcount["staffed_beds"].sum())
m1, m2, m3, m4 = st.columns(4)
with m1:
    st.metric("Facilities shown", f"{len(fcount):,}")
with m2:
    st.metric("Staffed beds", f"{beds_total:,}")
with m3:
    cah = (fcount["facility_type"] == "CAH").sum()
    st.metric("Critical Access (CAH)", f"{cah:,}")
with m4:
    tribal = (fcount["facility_type"] == "Tribal/IHS").sum()
    st.metric("Tribal / IHS", f"{tribal:,}")

# --------------------------------------------------------------------------
# Hospital roster
# --------------------------------------------------------------------------
section("Hospital roster",
        "Schema mirrors the CMS Provider of Services file plus the MT DPHHS "
        "facility roster — drop in real data with the same columns to switch "
        "from synthetic to live.")

with st.expander("Show the full roster"):
    st.dataframe(
        hosp[[
            "facility_id", "facility_name", "county_name", "facility_type",
            "ownership", "staffed_beds", "ccn", "rurality", "region",
        ]].sort_values(["facility_type", "facility_name"]),
        hide_index=True, use_container_width=True,
    )

# --------------------------------------------------------------------------
# Latest workforce snapshot
# --------------------------------------------------------------------------
section("County baseline panel — workforce snapshot (latest year)",
        "Where Montana's rural workforce stood at the close of the most recent "
        "year of available data. Use this view alongside the Workforce page to "
        "judge what 'meaningfully improved' means relative to baseline.")

latest_year = int(wf["year"].max())
wf_latest = wf[wf["year"] == latest_year].merge(
    counties[["fips", "county_name", "rurality", "region"]], on="fips")

c1, c2 = st.columns(2)
with c1:
    metric_choice = st.selectbox(
        "Metric to display",
        options=[
            ("np_per_100k", "Nurse practitioners per 100k"),
            ("md_per_100k", "Physicians per 100k"),
            ("rn_per_100k", "Registered nurses per 100k"),
            ("turnover_rate", "Annual provider turnover rate"),
            ("provider_mh_score", "Provider mental health score (1-10)"),
        ],
        format_func=lambda x: x[1],
    )
    metric_col, metric_label = metric_choice
with c2:
    rurality_filter = st.multiselect(
        "Show counties by rurality",
        options=["Urban", "Rural", "Tribal"],
        default=["Urban", "Rural", "Tribal"],
    )

display_df = wf_latest[wf_latest["rurality"].isin(rurality_filter)].copy()
display_df = display_df[["county_name", "rurality", "region", metric_col,
                         "population", "medicaid_share", "unemployment_pct"]]
display_df = display_df.rename(columns={
    "county_name": "County", "rurality": "Type", "region": "Region",
    metric_col: metric_label, "population": "Population",
    "medicaid_share": "Medicaid share", "unemployment_pct": "Unemployment %",
})
display_df = display_df.sort_values(metric_label,
                                    ascending=metric_col == "turnover_rate")
st.dataframe(display_df, hide_index=True, use_container_width=True, height=320)

# --------------------------------------------------------------------------
# Reading guide
# --------------------------------------------------------------------------
section("How a stakeholder should read this evaluation")

c1, c2, c3 = st.columns(3)
with c1:
    st.markdown(
        "**Step 1 — Implementation.** Did the intervention actually roll out? "
        "Each initiative page begins by showing the cumulative reach of the "
        "intervention in question. Weak downstream effects are hard to "
        "interpret if the intervention barely reached anyone."
    )
with c2:
    st.markdown(
        "**Step 2 — Effect.** Did treated units improve more than comparable "
        "untreated ones? The models on each page are causal: they use county "
        "or facility fixed effects to absorb stable differences, year fixed "
        "effects to absorb statewide trends, and event-study structure to test "
        "*when* effects appear."
    )
with c3:
    st.markdown(
        "**Step 3 — Synthesis.** Across all five initiatives, did Montana move "
        "materially closer to its FY2031 rural health goals on workforce, "
        "access, quality, financial sustainability, and tech/data capacity? "
        "**That is the program-level success question — and it is a synthesis "
        "of many imperfect estimates, not a single p-value.**"
    )

st.markdown("<br/>", unsafe_allow_html=True)
callout(
    "Built as a working draft of the RHTP evaluation tool. Every visualization, model, "
    "and statistical test is fully reproducible from the file at "
    "<code>/scripts/generate_data.py</code>. Replace files in <code>/data/</code> "
    "with real source data of the same schema to switch this dashboard from "
    "synthetic to live.",
    kind="info", title="About this dashboard",
)